Unverified50% confidenceBenchmarkExact time
On long-horizon difficult tasks, Opus rose from an 87% success rate at the low level to 97% at the x-high level, but the cost per task increased nearly 7-fold.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/8/2026
First Seen
Valid until: 11/22/2026
Sources
The Ultimate Guide to Claude Models and Effort: How to Save Tokens
youtubeWestPoint 11/7/2026
Related Entities
Related Claims
UnverifiedFrom low to the highest level, the cost and time of effort levels rise approximately exponentially, but the improvement in capability is not proportional.74% similarUnverifiedWhen the coding agent no longer generates its own tests, the task success rate improves, overall speed increases by approximately 6%, and costs decrease by approximately 9%.73% similarUnverifiedOn unseen composite tasks, AdaRSI increased the success rate from 4.6% to 13.8%, roughly a threefold relative improvement.70% similarUnverifiedIn 7 of the 12 model × task combinations, high only changed the price while accuracy stayed the same, with the cost per correct answer rising by 1.5 to 3.4 times.70% similarVerifiedIn a 10-step engineering task where each step has a 90% success rate, the overall task completion rate is approximately 35%; if each step's success rate is raised to 99%, the overall success rate jumps to 90%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1147916API
curl https://kongchang.com/api/v1/knowledge/claims/1147916MCP
get_claim(id=1147916)